Zobrazeno 1 - 10
of 276
pro vyhledávání: '"Scardapane, Simone"'
The deployment of large language models (LLMs) is often hindered by the extensive memory requirements of the Key-Value (KV) cache, especially as context lengths increase. Existing approaches to reduce the KV cache size involve either fine-tuning the
Externí odkaz:
http://arxiv.org/abs/2406.11430
Autor:
Telyatnikov, Lev, Bernardez, Guillermo, Montagna, Marco, Vasylenko, Pavlo, Zamzmi, Ghada, Hajij, Mustafa, Schaub, Michael T, Miolane, Nina, Scardapane, Simone, Papamarkou, Theodore
This work introduces TopoBenchmarkX, a modular open-source library designed to standardize benchmarking and accelerate research in Topological Deep Learning (TDL). TopoBenchmarkX maps the TDL pipeline into a sequence of independent and modular compon
Externí odkaz:
http://arxiv.org/abs/2406.06642
Autor:
Scardapane, Simone
Neural networks surround us, in the form of large language models, speech transcription systems, molecular discovery algorithms, robotics, and much more. Stripped of anything else, neural networks are compositions of differentiable primitives, and st
Externí odkaz:
http://arxiv.org/abs/2404.17625
In this paper, we propose a novel design for AI-native goal-oriented communications, exploiting transformer neural networks under dynamic inference constraints on bandwidth and computation. Transformers have become the standard architecture for pretr
Externí odkaz:
http://arxiv.org/abs/2405.02330
Influence based explainability of brain tumors segmentation in multimodal Magnetic Resonance Imaging
Autor:
Torda, Tommaso, Ciardiello, Andrea, Gargiulo, Simona, Grillo, Greta, Scardapane, Simone, Voena, Cecilia, Giagu, Stefano
In recent years Artificial Intelligence has emerged as a fundamental tool in medical applications. Despite this rapid development, deep neural networks remain black boxes that are difficult to explain, and this represents a major limitation for their
Externí odkaz:
http://arxiv.org/abs/2405.12222
Autor:
Scardapane, Simone, Baiocchi, Alessandro, Devoto, Alessio, Marsocci, Valerio, Minervini, Pasquale, Pomponi, Jary
Publikováno v:
Intelligenza Artificiale, vol. Pre-press, pp. 1-16, 2024
This article summarizes principles and ideas from the emerging area of applying \textit{conditional computation} methods to the design of neural networks. In particular, we focus on neural networks that can dynamically activate or de-activate parts o
Externí odkaz:
http://arxiv.org/abs/2403.07965
Autor:
Papamarkou, Theodore, Birdal, Tolga, Bronstein, Michael, Carlsson, Gunnar, Curry, Justin, Gao, Yue, Hajij, Mustafa, Kwitt, Roland, Liò, Pietro, Di Lorenzo, Paolo, Maroulas, Vasileios, Miolane, Nina, Nasrin, Farzana, Ramamurthy, Karthikeyan Natesan, Rieck, Bastian, Scardapane, Simone, Schaub, Michael T., Veličković, Petar, Wang, Bei, Wang, Yusu, Wei, Guo-Wei, Zamzmi, Ghada
Topological deep learning (TDL) is a rapidly evolving field that uses topological features to understand and design deep learning models. This paper posits that TDL is the new frontier for relational learning. TDL may complement graph representation
Externí odkaz:
http://arxiv.org/abs/2402.08871
Autor:
Strinati, Emilio Calvanese, Di Lorenzo, Paolo, Sciancalepore, Vincenzo, Aijaz, Adnan, Kountouris, Marios, Gündüz, Deniz, Popovski, Petar, Sana, Mohamed, Stavrou, Photios A., Soret, Beatriz, Cordeschi, Nicola, Scardapane, Simone, Merluzzi, Mattia, Zanzi, Lanfranco, Renato, Mauro Boldi, Quek, Tony, di Pietro, Nicola, Forceville, Olivier, Costanzo, Francesca, Li, Peizheng
Recent advances in AI technologies have notably expanded device intelligence, fostering federation and cooperation among distributed AI agents. These advancements impose new requirements on future 6G mobile network architectures. To meet these demand
Externí odkaz:
http://arxiv.org/abs/2402.07573
Autor:
Hajij, Mustafa, Papillon, Mathilde, Frantzen, Florian, Agerberg, Jens, AlJabea, Ibrahem, Ballester, Ruben, Battiloro, Claudio, Bernárdez, Guillermo, Birdal, Tolga, Brent, Aiden, Chin, Peter, Escalera, Sergio, Fiorellino, Simone, Gardaa, Odin Hoff, Gopalakrishnan, Gurusankar, Govil, Devendra, Hoppe, Josef, Karri, Maneel Reddy, Khouja, Jude, Lecha, Manuel, Livesay, Neal, Meißner, Jan, Mukherjee, Soham, Nikitin, Alexander, Papamarkou, Theodore, Prílepok, Jaro, Ramamurthy, Karthikeyan Natesan, Rosen, Paul, Guzmán-Sáenz, Aldo, Salatiello, Alessandro, Samaga, Shreyas N., Scardapane, Simone, Schaub, Michael T., Scofano, Luca, Spinelli, Indro, Telyatnikov, Lev, Truong, Quang, Walters, Robin, Yang, Maosheng, Zaghen, Olga, Zamzmi, Ghada, Zia, Ali, Miolane, Nina
We introduce TopoX, a Python software suite that provides reliable and user-friendly building blocks for computing and machine learning on topological domains that extend graphs: hypergraphs, simplicial, cellular, path and combinatorial complexes. To
Externí odkaz:
http://arxiv.org/abs/2402.02441
Humans are capable of acquiring new knowledge and transferring learned knowledge into different domains, incurring a small forgetting. The same ability, called Continual Learning, is challenging to achieve when operating with neural networks due to t
Externí odkaz:
http://arxiv.org/abs/2402.01262